-
Notifications
You must be signed in to change notification settings - Fork 618
[JDBC-v2] Fix parser to property handle keywords in aliases and table names #2725
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
c458a08
1974fe4
6c6d1da
a04e948
851e3b7
05d912c
0654a59
0592ef7
d4be072
92b5811
c6a6ad7
e955542
93a93be
26d0012
a4ca320
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Large diffs are not rendered by default.
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -49,6 +49,13 @@ public class ClickHouseSqlParser { | |
|
|
||
| private static final Logger log = LoggerFactory.getLogger(ClickHouseSqlParser.class); | ||
|
|
||
| private static final Set<String> ALLOWED_ALIAS_KEYWORDS = | ||
| ClickHouseSqlUtils.getKeywordGroup(ClickHouseSqlUtils.KEYWORD_GROUP_ALLOWED_ALIASES); | ||
|
|
||
| private static boolean isAllowedAlias(Token t) { | ||
| return t != null && ALLOWED_ALIAS_KEYWORDS.contains(t.image.toUpperCase(Locale.ROOT)); | ||
| } | ||
|
|
||
| private final List<ClickHouseSqlStatement> statements = new ArrayList<>(); | ||
|
|
||
| private ParseHandler handler; | ||
|
|
@@ -520,7 +527,12 @@ void deleteStmt(): {} { | |
| // https://clickhouse.tech/docs/en/sql-reference/statements/describe-table/ | ||
| void describeStmt(): {} { | ||
| (<DESCRIBE> | <DESC>) { token_source.table = "columns"; } | ||
| (LOOKAHEAD({ getToken(1).kind == TABLE }) <TABLE>)? tableIdentifier(true) (anyExprList())? | ||
| (LOOKAHEAD({ getToken(1).kind == TABLE }) <TABLE>)? | ||
| ( | ||
| LOOKAHEAD({ getToken(1).kind == LPAREN }) <LPAREN> anyExprList() <RPAREN> | ||
| | tableIdentifier(true) | ||
| ) | ||
| (anyExprList())? | ||
| } | ||
|
|
||
| // https://clickhouse.tech/docs/en/sql-reference/statements/detach/ | ||
|
|
@@ -575,8 +587,13 @@ void grantStmt(): {} { // not interested | |
| void insertStmt(): {} { | ||
| <INSERT> <INTO> | ||
| ( | ||
| LOOKAHEAD({ getToken(1).kind == FUNCTION }) <FUNCTION> functionExpr() | ||
| | (LOOKAHEAD(2) <TABLE>)? tableIdentifier(true) | ||
| LOOKAHEAD({ getToken(1).kind == FUNCTION | ||
| && !tokenIn(2, VALUES, FORMAT, SETTINGS, SELECT, WITH, INFILE) | ||
| && getToken(3).kind == LPAREN }) <FUNCTION> functionExpr() | ||
| | ( | ||
| LOOKAHEAD({ getToken(1).kind == TABLE | ||
| && !tokenIn(2, VALUES, FORMAT, SETTINGS, SELECT, WITH, LPAREN) }) <TABLE> | ||
| )? tableIdentifier(true) | ||
| ) | ||
| ( | ||
| LOOKAHEAD(2) infilePart() | ||
|
|
@@ -678,6 +695,7 @@ void showStmt(): {} { | |
| (<DATABASE> databaseIdentifier(true)) | ||
| | LOOKAHEAD(2) (LOOKAHEAD(1) <CREATE>)? (LOOKAHEAD(1) <SETTINGS>)? <PROFILE> anyIdentifier() | ||
| | LOOKAHEAD(2) (<DICTIONARY> tableIdentifier(true)) | ||
| | LOOKAHEAD(2) (LOOKAHEAD(1) <CHANGED>)? <SETTINGS> { token_source.table = "settings"; } | ||
| | LOOKAHEAD(2) ((LOOKAHEAD(2) <TEMPORARY>)? (LOOKAHEAD(2) <TABLE>)? tableIdentifier(true)) | ||
| ) | ||
| ) | ||
|
|
@@ -725,12 +743,12 @@ void columnExprList(): {} { | |
|
|
||
| void withExpr(): {} { | ||
| nestedExpr() | ||
| (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)* | ||
| ( | ||
| ( | ||
| LOOKAHEAD({ getToken(1).kind == FLOATING_LITERAL }) | ||
| <FLOATING_LITERAL> | <DOT> <DECIMAL_LITERAL> | ||
| )+ | ||
| | (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)+ | ||
| | LOOKAHEAD(2) <IS> (<NOT>)? <NULL> | ||
| | LOOKAHEAD(2) (<NOT>)? betweenExpr() | ||
| | LOOKAHEAD(2) (<NOT>)? (<ILIKE> | <LIKE>) nestedExpr() | ||
|
|
@@ -747,12 +765,12 @@ void columnsExpr(): {} { | |
| LOOKAHEAD(2) (<APPLY> | <EXCEPT> | <REPLACE>) <LPAREN> anyExprList() <RPAREN> | ||
| )* | ||
| | nestedExpr() | ||
| (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)* | ||
| ( | ||
| ( | ||
| LOOKAHEAD({ getToken(1).kind == FLOATING_LITERAL }) | ||
| <FLOATING_LITERAL> | <DOT> <DECIMAL_LITERAL> | ||
| )+ | ||
| | (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)+ | ||
| | LOOKAHEAD(2) <IS> (<NOT>)? <NULL> | ||
| | LOOKAHEAD(2) (<NOT>)? betweenExpr() | ||
| | LOOKAHEAD(2) (<NOT>)? (<ILIKE> | <LIKE>) nestedExpr() | ||
|
|
@@ -773,11 +791,11 @@ void nestedExpr(): {} { | |
| (<WHEN> nestedExpr() <THEN> nestedExpr())+ (<ELSE> nestedExpr())? <END> | ||
| | LOOKAHEAD(2) <INTERVAL> (LOOKAHEAD(2) <STRING_LITERAL> | nestedExpr() interval()) | ||
| | columnExpr() | ||
| (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)* | ||
| ( | ||
| ( | ||
| <FLOATING_LITERAL> | <DOT> <DECIMAL_LITERAL> | ||
| )+ | ||
| | (LOOKAHEAD(2) <LBRACKET> anyExprList() <RBRACKET>)+ | ||
| | LOOKAHEAD(2) <IS> (<NOT>)? <NULL> | ||
| | LOOKAHEAD(2) (<NOT>)? betweenExpr() | ||
| | LOOKAHEAD(2) (<NOT>)? (<ILIKE> | <LIKE>) nestedExpr() | ||
|
|
@@ -843,7 +861,7 @@ void outfilePart(): {} { | |
| } | ||
|
|
||
| void settingsPart(): {} { | ||
| <SETTINGS> { token_source.addPosition(token); } settingExprList() | ||
| (LOOKAHEAD(1) <CHANGED>)? <SETTINGS> { token_source.addPosition(token); } (LOOKAHEAD(2) settingExprList())? | ||
chernser marked this conversation as resolved.
Show resolved
Hide resolved
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Optional settingExprList silently consumes bare SETTINGS keyword everywhereMedium Severity Making |
||
| } | ||
|
|
||
| void withTotalPart(): {} { | ||
|
|
@@ -888,13 +906,25 @@ void anyColumnExpr(): {} { | |
| | nestedIdentifier() | ||
| } | ||
|
|
||
| Token aliasIdentifier(): { Token t; } { | ||
| ( | ||
| t = <IDENTIFIER> | ||
| | t = <BACK_QUOTED_NAME> | ||
| | t = <DOUBLE_QUOTED_NAME> | ||
| | t = variable() | ||
| | LOOKAHEAD({ isAllowedAlias(getToken(1)) }) | ||
| t = anyKeyword() | ||
| ) | ||
| { return t; } | ||
| } | ||
|
|
||
| Token aliasExpr(): { Token t = null; } { | ||
| ( | ||
| LOOKAHEAD(2) <AS> t = anyIdentifier() | ||
| LOOKAHEAD(2) <AS> t = aliasIdentifier() | ||
| | LOOKAHEAD(2) formatPart() | ||
| | LOOKAHEAD(2) settingsPart() | ||
| | LOOKAHEAD(2) outfilePart() | ||
| | t = identifier() | ||
| | t = aliasIdentifier() | ||
| ) | ||
| { return t; } | ||
| } | ||
|
|
@@ -950,10 +980,12 @@ void settingExprList(): {} { | |
| } | ||
|
|
||
| void settingExpr(): { String key; } { | ||
| identifier() { key = token.image; } <EQ_SINGLE> literal() { token_source.addSetting(key, token.image); } | ||
| anyIdentifier() { key = token.image; } <EQ_SINGLE> literal() { token_source.addSetting(key, token.image); } | ||
| } | ||
|
|
||
| // basics | ||
| // --- Base definitions | ||
|
|
||
|
|
||
| Token anyIdentifier(): { Token t; } { | ||
| ( | ||
| t = <BACK_QUOTED_NAME> | ||
|
|
@@ -965,17 +997,6 @@ Token anyIdentifier(): { Token t; } { | |
| { return t; } | ||
| } | ||
|
|
||
| Token identifier(): { Token t; } { | ||
| ( | ||
| t = <BACK_QUOTED_NAME> | ||
| | t = <DOUBLE_QUOTED_NAME> | ||
| | t = variable() | ||
| | t = <IDENTIFIER> | ||
| | t = keyword() | ||
| ) | ||
| { return t; } | ||
| } | ||
|
|
||
| void interval(): {} { | ||
| <SECOND> | <MINUTE> | <HOUR> | <DAY> | <WEEK> | <MONTH> | <QUARTER> | <YEAR> | ||
| } | ||
|
|
@@ -1045,15 +1066,15 @@ Token anyKeyword(): { Token t; } { | |
| | t = <MOVE> | t = <OPTIMIZE> | t = <RENAME> | t = <REVOKE> | t = <SELECT> | t = <SET> | t = <SHOW> | t = <SYSTEM> | ||
| | t = <TRUNCATE> | t = <UPDATE> | t = <USE> | t = <WATCH> | t = <UNDROP> | ||
| // others | ||
| | t = <ALL> | t = <AND> | t = <APPLY> | t = <ARRAY> | t = <AS> | t = <ASOF> | t = <BETWEEN> | t = <CASE> | ||
| | t = <CLUSTER> | t = <COMPRESSION> | t = <DATE> | t = <DATABASE> | t = <DATABASES> | t = <DICTIONARY> | t = <DICTIONARIES> | ||
| | t = <ALL> | t = <AND> | t = <APPLY> | t = <ARRAY> | t = <AS> | t = <ASOF> | t = <BEGIN> | t = <BETWEEN> | t = <CASE> | t = <CHANGED> | ||
| | t = <CLUSTER> | t = <COMMIT> | t = <COMPRESSION> | t = <DATE> | t = <DATABASE> | t = <DATABASES> | t = <DICTIONARY> | t = <DICTIONARIES> | ||
| | t = <DISTINCT> | t = <ELSE> | t = <END> | t = <EXCEPT> | t = <FORMAT> | t = <FROM> | t = <FINAL> | t = <FULL> | ||
| | t = <FUNCTION> | t = <GLOBAL> | t = <GROUP> | t = <HAVING> | t = <IF> | t = <ILIKE> | t = <IN> | t = <INFILE> | t = <INNER> | ||
| | t = <INPUT> | t = <INTERVAL> | t = <INTO> | t = <IS> | t = <LEVEL> | t = <JOIN> | t = <LEFT> | t = <LIKE> | t = <LIMIT> | t = <LIVE> | ||
| | t = <MATERIALIZED> | t = <NOT> | t = <OFFSET> | t = <ON> | t = <OR> | t = <ORDER> | t = <OUTFILE> | t = <POLICY> | ||
| | t = <PREWHERE> | t = <PROFILE> | t = <QUOTA> | t = <REPLACE> | t = <RIGHT> | t = <ROLE> | t = <ROW> | t = <SAMPLE> | ||
| | t = <PREWHERE> | t = <PROFILE> | t = <QUOTA> | t = <REPLACE> | t = <RIGHT> | t = <ROLE> | t = <ROLLBACK> | t = <ROW> | t = <SAMPLE> | ||
| | t = <SETTINGS> | t = <STDOUT> | t = <TEMPORARY> | t = <TABLE> | t = <TABLES> | t = <THEN> | t = <TIES> | t = <TIMESTAMP> | ||
| | t = <TOP> | t = <TOTALS> | t = <VALUES> | t = <VIEW> | t = <USER> | t = <UNION> | t = <USING> | ||
| | t = <TOP> | t = <TOTALS> | t = <TRANSACTION> | t = <VALUES> | t = <VIEW> | t = <USER> | t = <UNION> | t = <USING> | ||
| | t = <WHEN> | t = <WHERE> | t = <WITH> | t = <REGEXP> | ||
| // interval | ||
| | t = <SECOND> | t = <MINUTE> | t = <HOUR> | t = <DAY> | t = <WEEK> | t = <MONTH> | t = <QUARTER> | t = <YEAR> | ||
|
|
@@ -1063,32 +1084,11 @@ Token anyKeyword(): { Token t; } { | |
| { return t; } | ||
| } | ||
|
|
||
| Token keyword(): { Token t; } { | ||
| ( | ||
| // leading keywords(except with) | ||
| t = <ALTER> | t = <ATTACH> | t = <CHECK> | t = <CREATE> | t = <DELETE> | t = <DESC> | t = <DESCRIBE> | ||
| | t = <DETACH> | t = <DROP> | t = <EXCHANGE> | t = <EXISTS> | t = <EXPLAIN> | t = <GRANT> | t = <INSERT> | t = <KILL> | ||
| | t = <MOVE> | t = <OPTIMIZE> | t = <RENAME> | t = <REVOKE> | t = <SELECT> | t = <SET> | t = <SHOW> | t = <SYSTEM> | ||
| | t = <TRUNCATE> | t = <UPDATE> | t = <USE> | t = <WATCH> | t = <UNDROP> | ||
| // others | ||
| | t = <CASE> | t = <CLUSTER> | t = <DATE> | t = <DATABASE> | t = <DATABASES> | t = <DICTIONARY> | ||
| | t = <DICTIONARIES> | t = <DISTINCT> | t = <ELSE> | t = <END> | t = <EXCEPT>| t = <FUNCTION> | ||
| | t = <IF> | t = <INTERVAL> | t = <IS> | t = <INFILE> | t = <LIVE> | t = <MATERIALIZED> | t = <OUTFILE> | t = <POLICY> | ||
| | t = <PROFILE> | t = <QUOTA> | t = <REPLACE> | t = <ROLE> | t = <ROW> | t = <TEMPORARY> | ||
| | t = <TABLE> | t = <TABLES> | t = <THEN> | t = <TIES> | t = <TIMESTAMP> | t = <TOP> | t = <TOTALS> | ||
| | t = <VALUES> | t = <VIEW> | t = <WHEN> | t = <USER> | t = <REGEXP> | ||
| // interval | ||
| | t = <SECOND> | t = <MINUTE> | t = <HOUR> | t = <DAY> | t = <WEEK> | t = <MONTH> | t = <QUARTER> | t = <YEAR> | ||
| // values | ||
| | t = <INF> | t = <NAN> | t = <NULL> | ||
| ) | ||
| { return t; } | ||
| } | ||
|
|
||
| // keywords | ||
| TOKEN: { | ||
| <ALTER : <A> <L> <T> <E> <R>> | ||
| | <ATTACH : <A> <T> <T> <A> <C> <H> > | ||
| | <CHANGED : <C> <H> <A> <N> <G> <E> <D> > | ||
| | <CHECK : <C> <H> <E> <C> <K> > | ||
| | <CREATE : <C> <R> <E> <A> <T> <E> > | ||
| | <DELETE : <D> <E> <L> <E> <T> <E> > | ||
|
|
||


There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Inconsistent FLOATING_LITERAL LOOKAHEAD across three expression functions
Low Severity
The
LBRACKEThandling was moved outside the choice block identically inwithExpr(),columnsExpr(), andnestedExpr(). However, theLOOKAHEAD({ getToken(1).kind == FLOATING_LITERAL })guard was added before<FLOATING_LITERAL>inwithExpr()andcolumnsExpr()but omitted innestedExpr(). All three functions share the same structural pattern for this code block, so the inconsistent application of the fix is surprising and could confuse future maintainers.Additional Locations (2)
jdbc-v2/src/main/javacc/ClickHouseSqlParser.jj#L748-L750jdbc-v2/src/main/javacc/ClickHouseSqlParser.jj#L770-L772